Optimal Feature Selection from High-dimensional Microarray Dataset Employing Hybrid IG-Jaya Model

Abstract

Background: Feature selection (FS) is a crucial strategy for dimensionality reduction in data preprocessing since microarray data sets typically contain redundant and extraneous features that degrade the performance and complexity of classification models. Objective: The purpose of feature selection is to reduce the number of features from highdimensional cancer datasets and enhance classification accuracy. Methods: This research provides a wrapper-based hybrid model integrating information gain (IG) and Jaya algorithm (JA) for determining the optimum featured genes from high-dimensional microarray datasets. This paper's comprehensive study is divided into two segments: we employed the parameterless JA to identify the featured gene subsets in the first stage without filter methods. Various classifiers evaluate JA's performance, such as SVM, LDA, NB, and DT. In the second section, we introduce a hybrid IG-JA model. The IG is used as a filter to eliminate redundant and noisy features. The reduced feature subset is then given to the JA as a wrapper to improve the hybrid model's performance using the classifiers outlined above. Results: We used 13 benchmark microarray data sets from the public repository for experimental analysis. It is noteworthy to state that the hybrid IG-JA model performs better as compared to its counterparts. Conclusion: Tests and statistics show that the suggested model outperforms the standard feature selection method with JA and other existing models. Our proposed model is unable to provide the best accuracy compared to other existing approaches; however, it is quite steady and good. In the future, this work could be implemented with various filter methods and real-time data sets. A multi-filter approach with the Jaya algorithm will be used to check the efficiency of the proposed one. And it would be better to choose any other hybrid model (chaos-based) with Jaya to enhance the feature selection accuracy with a high dimensional dataset.